TY - JOUR
T1 - Individuality of a group
T2 - detailed walking ability analysis of broiler flocks using optical flow approach
AU - van der Eijk, Jerine A.J.
AU - Guzhva, Oleksiy
AU - Schulte-Landwehr, Jan
AU - Giersberg, Mona F.
AU - Jacobs, Leonie
AU - de Jong, Ingrid C.
N1 - Funding Information:
The present study was supported by the Foundation for Food & Agriculture Research (FFAR) and McDonald's within the SMART broiler program under award number Sb-0000000016. The content of this publication is solely the responsibility of the authors and does not necessarily represent the official views of the Foundation for Food & Agriculture Research or McDonald's.
Publisher Copyright:
© 2023 The Author(s)
PY - 2023/10
Y1 - 2023/10
N2 - Impaired walking ability is one of the most important factors affecting broiler welfare. Routine monitoring of walking ability provides insights in the welfare status of a flock and assists farmers in taking remedial measures at an early stage. Several computer vision techniques have been developed for automated assessment of walking ability, providing an objective and biosecure alternative to the currently more subjective and time-consuming manual assessment of walking ability. However, these techniques mainly focus on assessment of averages at flock level using pixel movement. Therefore, the aim of this study was to investigate the potential of optical flow algorithms to identify flock activity, distribution and walking ability in a commercial setting on levels close to individual monitoring. We used a combination of chicken segmentation and optical flow methods, where chicken contours were first detected and were then used to identify activity, spatial distribution, and gait score distribution (i.e. walking ability) of the flock via optical flow. This is a step towards focusing more on individual chickens in an image and its pixel representation. In addition, we predicted the gait score distribution of the flock, which is a more detailed assessment of broiler walking ability compared to average gait score of the flock, as slight changes in walking ability are more likely to be detected when using the distribution compared to the average score. We found a strong correlation between predicted and observed gait scores (R2 = 0.97), with separate gait scores all having R2 > 0.85. Thus, the algorithm used in this study is a first step to measure broiler walking ability automatically in a commercial setting on a levels close to individual monitoring. These validation results of the developed automatic monitoring of flock activity, distribution and gait score are promising, but further validation is required (e.g. for chickens at a younger age, with very low and very high gait scores).
AB - Impaired walking ability is one of the most important factors affecting broiler welfare. Routine monitoring of walking ability provides insights in the welfare status of a flock and assists farmers in taking remedial measures at an early stage. Several computer vision techniques have been developed for automated assessment of walking ability, providing an objective and biosecure alternative to the currently more subjective and time-consuming manual assessment of walking ability. However, these techniques mainly focus on assessment of averages at flock level using pixel movement. Therefore, the aim of this study was to investigate the potential of optical flow algorithms to identify flock activity, distribution and walking ability in a commercial setting on levels close to individual monitoring. We used a combination of chicken segmentation and optical flow methods, where chicken contours were first detected and were then used to identify activity, spatial distribution, and gait score distribution (i.e. walking ability) of the flock via optical flow. This is a step towards focusing more on individual chickens in an image and its pixel representation. In addition, we predicted the gait score distribution of the flock, which is a more detailed assessment of broiler walking ability compared to average gait score of the flock, as slight changes in walking ability are more likely to be detected when using the distribution compared to the average score. We found a strong correlation between predicted and observed gait scores (R2 = 0.97), with separate gait scores all having R2 > 0.85. Thus, the algorithm used in this study is a first step to measure broiler walking ability automatically in a commercial setting on a levels close to individual monitoring. These validation results of the developed automatic monitoring of flock activity, distribution and gait score are promising, but further validation is required (e.g. for chickens at a younger age, with very low and very high gait scores).
KW - activity
KW - broiler welfare
KW - computer vision
KW - distribution
KW - optical flow
KW - walking ability
UR - http://www.scopus.com/inward/record.url?scp=85167573096&partnerID=8YFLogxK
U2 - 10.1016/j.atech.2023.100298
DO - 10.1016/j.atech.2023.100298
M3 - Article
AN - SCOPUS:85167573096
SN - 2772-3755
VL - 5
JO - Smart Agricultural Technology
JF - Smart Agricultural Technology
M1 - 100298
ER -